Security MCP servers

Fail-closed approval layer for unattended agent runs: checks actions against org policy, requests human approval and logs every decision to a causal ledger.

Agent compliance and identity: verify an agent's X.509 certificate scope, read its behavioral risk score and append to an immutable audit trail.

SSRF-hardened web gateway with web fetch, web search and Metis verification, sharing an audited security core with Metis and ARGUS.

Query ARGUS-3 and check its status; WARDEN vets third-party MCP servers with a scored firewall, tool-definition pinning and drift detection.

Agent identity, scoped delegation and governance: issue passports, verify narrowing-only delegation chains, enforce gateway policy and emit signed records.

Agent identity registry (reputation, capability search, task marketplace, messaging) plus a local encrypted vault that leases provider keys to agents.

MINT Protocol work attestation for agents: cryptographically attest, verify, rate and discover agent work to build portable on-chain reputation.

Scan and fix a domain's email authentication (SPF, DMARC, DKIM, MX), blacklist status and domain/SSL expiry, with deterministic, validated fix records.

Keyless, read-only CVE and internet-exposure intelligence: CVE lookup and search, CISA KEV, EPSS history, CWE, vendor advisories (MSRC, Red Hat, Cisco, GHSA and more), SBOM and manifest checks, and aggregate exposure rad

Attack-path engine for cloud and Kubernetes: list routes from internet exposure to sensitive assets, explain each hop, find choke points and simulate fixes.

Accountability for AI agent fleets: verify a signed, hash-chained ledger, check budgets, kill an agent, and issue passports and mandates, all through the local CLI.

Mobb Vibe Shield identifies and remediates vulnerabilities in human and AI-written code.

Use Panther's SIEM platform in natural language to write detections, query logs and manage alerts.

Locally check npm and PyPI packages, such as those suggested by AI coding tools, for vulnerabilities and malicious code.

Manage Scalekit organizations, users and SSO.

Algenta decision engine: dataset discovery, exact queries, utility models, decision memory and governed agent runs with approvals and execution receipts.

Self-hostable human-in-the-loop approval inbox: humans approve, reject or edit proposed agent actions via web, mobile, Slack, Discord or Telegram.

Scan code for security vulnerabilities using Semgrep.

Embeds Snyk's security engines into agentic workflows to secure AI-generated code in real time and work through vulnerability backlogs faster.

Classify input for prompt injection and out-of-scope content with Koma Gate's LLM-based classifier.

Analyze AWS IAM policies and CloudFormation templates with Shieldly to flag privilege-escalation paths, wildcards and over-permissive access.

Check the reputation of AI microservices and public APIs before calling them and submit ratings afterward, via an open trust registry.

Author, lint, validate and convert Sigma detection rules with RSigma, evaluate and explain detections against log events, and inspect correlation state.